Related papers: Autoregressive Image Generation with Masked Bit Mo…

Current image captioning works usually focus on generating descriptions in an autoregressive manner. However, there are limited works that focus on generating descriptions non-autoregressively, which brings more decoding diversity. Inspired…

Image tokenizers form the foundation of modern text-to-image generative models but are notoriously difficult to train. Furthermore, most existing text-to-image models rely on large-scale, high-quality private datasets, making them…

Autoregressive (AR) models have long dominated the landscape of large language models, driving progress across a wide range of tasks. Recently, diffusion-based language models have emerged as a promising alternative, though their advantages…

Masked Image Generation Models (MIGMs) have achieved great success, yet their efficiency is hampered by the multiple steps of bi-directional attention. In fact, there exists notable redundancy in their computation: when sampling discrete…

Visual Autoregressive (VAR) models enable efficient image generation via next-scale prediction but face escalating computational costs as sequence length grows. Existing static pruning methods degrade performance by permanently removing…

Monocular depth estimation has seen significant advances through discriminative approaches, yet their performance remains constrained by the limitations of training datasets. While generative approaches have addressed this challenge by…

Watermarking the outputs of generative models has emerged as a promising approach for tracking their provenance. Despite significant interest in autoregressive image generation models and their potential for misuse, no prior work has…

Monocular depth estimation can benefit from autoregressive (AR) generation, but direct AR modeling is hindered by the modality gap between RGB and depth, inefficient pixel-wise generation, and instability in continuous depth prediction. We…

Evaluating the performance of generative models in image synthesis is a challenging task. Although the Fr\'echet Inception Distance is a widely accepted evaluation metric, it integrates different aspects (e.g., fidelity and diversity) of…

Learned progressive image compression is gaining momentum as it allows improved image reconstruction as more bits are decoded at the receiver. We propose a progressive image compression method in which an image is first represented as a…

We introduce LlamaGen, a new family of image generation models that apply original ``next-token prediction'' paradigm of large language models to visual generation domain. It is an affirmative answer to whether vanilla autoregressive…

Text and faces are among the most perceptually salient and practically important patterns in visual generation, yet they remain challenging for autoregressive generators built on discrete tokenization. A central bottleneck is the tokenizer:…

Autoregressive Transformer models have demonstrated impressive performance in video generation, but their sequential token-by-token decoding process poses a major bottleneck, particularly for long videos represented by tens of thousands of…

Autoregressive (AR) modeling, known for its next-token prediction paradigm, underpins state-of-the-art language and visual generative models. Traditionally, a ``token'' is treated as the smallest prediction unit, often a discrete symbol in…

Videos are inherently temporal sequences by their very nature. In this work, we explore the potential of modeling videos in a chronological and scalable manner with autoregressive (AR) language models, inspired by their success in natural…

Autoregressive (AR) language models generate text one token at a time, even when consecutive tokens are highly predictable given earlier context. We introduce MARS (Mask AutoRegreSsion), a lightweight fine-tuning method that teaches an…

Visual tokenizers are fundamental to image generation. They convert visual data into discrete tokens, enabling transformer-based models to excel at image generation. Despite their success, VQ-based tokenizers like VQGAN face significant…

Self-supervised learning methods like masked autoencoders (MAE) have shown significant promise in learning robust feature representations, particularly in image reconstruction-based pretraining task. However, their performance is often…

We investigate methods to reduce inference time and memory footprint in stable diffusion models by introducing lightweight decoders for both image and video synthesis. Traditional latent diffusion pipelines rely on large Variational…

Masked diffusion models (MDMs) have emerged as a promising approach for language modeling, yet they face a performance gap compared to autoregressive models (ARMs) and require more training iterations. In this work, we present the…